23 lines
660 B
Scala
23 lines
660 B
Scala
package date_20250401
|
|
|
|
import org.apache.spark.rdd.RDD
|
|
import org.apache.spark.{SparkConf, SparkContext}
|
|
|
|
object task2 {
|
|
def main(args: Array[String]): Unit = {
|
|
val conf: SparkConf = new SparkConf().setMaster("local").setAppName("testRdd")
|
|
|
|
val sc = new SparkContext(conf)
|
|
|
|
val data: RDD[String] = sc.textFile("/Volumes/Data/04CodeData/gcc-project-25-2/spark-lesson/src/main/scala/date_20250401/data/word")
|
|
|
|
data.flatMap(_.split(" "))
|
|
.map(x => (x, 1))
|
|
.reduceByKey(_ + _)
|
|
.sortBy(_._2, false)
|
|
.collect()
|
|
.foreach(println)
|
|
|
|
}
|
|
}
|